Triple
T37772870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Autobahn A6 |
E941598
|
entity |
| Predicate | connectsUrbanRegion |
P97106
|
FINISHED |
| Object | Saarbrücken urban area |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Saarbrücken urban area | Statement: [Autobahn A6, connectsUrbanRegion, Saarbrücken urban area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: connectsUrbanRegion Context triple: [Autobahn A6, connectsUrbanRegion, Saarbrücken urban area]
-
A.
connectsMetroAreas
Indicates a relationship where a transportation route or service links two or more metropolitan areas, enabling direct travel or interaction between them.
-
B.
connectsCity
Indicates a relationship where one entity serves as a link or route that joins or provides direct access between two cities.
-
C.
connectsRegionalCity
Indicates a relationship where one entity serves as a link or transport route between a regional city and another location.
-
D.
formsUrbanAreaWith
Indicates that two or more settlements are geographically and functionally connected so that together they constitute a single continuous urban area.
-
E.
connectsToUrbanCenter
chosen
Indicates that one entity has a direct or functional linkage to an urban center, such as through infrastructure, services, or regular interaction.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76ee4431881908f87e8892a9f39f3 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a000014497c819088d5cda3977522dd |
completed | May 10, 2026, 3:48 a.m. |
| PD | Predicate disambiguation | batch_69ffff9a52b08190be1024e0fb6fe661 |
completed | May 10, 2026, 3:46 a.m. |
Created at: May 3, 2026, 4:19 p.m.